Tag: #agents
Writing on GPUs, LLMs, MLOps, Kubernetes — and mindset · 10 posts
Running AI Agents in Production — Idempotency, Budgets, and Confidently Wrong Answers
Moving an agent from prototype to production exposes an operational surface you only discover late: idempotency for retried tool calls, budgets and step limits, observability over non-deterministic control flow, per-tool
2026-07-31 · 16 min read #ai#agents#observability#reliability#mcpHow AI Agents Fail in Production — 14 Failure Modes, and Why Retrying Is Not Safe
Putting agents in production hurts in three places. First, failures come from system design, not the model — UC Berkeley's MAST study classified 1642 execution traces into 14 failure modes, and 44.2% of them were system-
2026-07-17 · 20 min read #ai#agents#observability#reliability#mcpSimulated Customers Never Walk Away — Where LLM User Simulators Inflate Agent Scores
In τ-bench-style conversational agent benchmarks, the 'user' role is played by another LLM. But this simulator isn't the thing being measured — it's the measuring instrument, and instruments need calibration. Three verif
2026-07-16 · 21 min read #ai#llm#evaluation#agents#simulationMCP Drops Sessions — Reading the Stateless Core in the 2026-07-28 Revision
The next MCP specification revision, 2026-07-28, is the biggest change since launch. Its core move is stripping state out of the protocol layer — the initialize handshake and Mcp-Session-Id sessions disappear, and every
2026-07-16 · 16 min read #mcp#ai#protocol#agents#integrationWhat a Good Agent Benchmark Looks Like in 2026 — UniClawBench, Live Containers, and a Hidden Supervisor
UniClawBench, posted to arXiv in July 2026 by HKU MMLab, is a self-described capability-driven benchmark for proactive agents. Instead of matching against static, pre-recorded answers, it runs agents inside live Docker c
2026-07-11 · 5 min read #ai#agents#evaluation#benchmark#llmThe Model Context Protocol (MCP): An Engineer's Reference
The Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to LLMs. This is an engineer's reference grounded in the official docs: why it solves the M×N integration problem, t
2026-07-11 · 6 min read #mcp#ai#agents#llm#protocolReading Microsoft Flint — a Visualization Language for Agents to Draw Charts, Not to Be Drawn
Microsoft Research's Flint is not a language for visualizing agents — it is an intermediate language that lets AI agents reliably produce good-looking charts from data. A compiler derives the low-level decisions (scales,
2026-07-11 · 5 min read #ai#agents#data-visualization#llm#microsoftCoding Benchmarks Are Misaligned with the Agent Era — Three Reasons Leaderboards Compare Agents Wrong
A position paper from a Tessl team, posted to arXiv in June 2026, argues that today's coding benchmarks are fundamentally misaligned with agentic software engineering. Benchmarks were built to measure a single model, yet
2026-07-11 · 5 min read #ai#agents#evaluation#software-engineering#coding-benchmarksChoosing How Much to Think Per Step: Ares and Adaptive Reasoning-Effort Routing
A practical look at Ares, a March 2026 preprint that treats reasoning effort as a per-step cost lever for LLM agents. A lightweight router reads the interaction history and predicts the lowest sufficient reasoning level
2026-07-11 · 4 min read #ai#agents#llm#efficiencyBuilding Effective AI Agents: A Reference on the Five Workflow Patterns and Agents
A practical reference distilled from Anthropic's engineering guide "Building Effective Agents." It covers the precise distinction between workflows and agents, the building block underneath everything — the augmented LLM
2026-07-11 · 8 min read #ai#agents#llm#engineering#anthropic